AI generation API for image, video, and audio
Build on a versioned AI generation API that shares the exact same pipeline as the dashboard - the same image, video, and audio models, credits, limits, storage, and billing rules.
See it in action
Real captures from the platform: a live generation running end to end, the API-key screen, and the finished result.
Typical flow
Create an API key
API keys are created in the dashboard with per-key scopes, so you can grant least-privilege access to each service.
Upload and generate
Upload files with presigned URLs, then submit generations with the Idempotency-Key header for safe retries.
Poll or get webhooks
Poll generation status or subscribe to webhooks for terminal states, delivered with an HMAC-SHA256 signature.
Track usage
Every request is rate-limited per key, logged, and reportable through the usage endpoint — credits, latency, and errors.
Core endpoints
| Method | Path | Purpose |
|---|---|---|
| POST | /v1/files/upload-url | Get a presigned upload URL |
| GET | /v1/models | List plan-aware models |
| POST | /v1/generations | Create a generation (idempotent) |
| GET | /v1/generations/:id | Generation detail + events |
| POST | /v1/generations/:id/cancel | Cancel an active job |
| GET | /v1/usage | Usage and quota summary |
| GET | /v1/wallet | Pay-as-you-go wallet balance |
| POST | /v1/webhooks | Manage delivery endpoints |
What you get
- Scoped API keys with revocation and expiry
- Per-key rate limits with X-RateLimit headers
- Idempotency for safe retries and automation
- Signed webhooks with delivery history and retries
- Usage reporting: requests, errors, latency, credits
- A 90-day deprecation policy for breaking changes
The interactive OpenAPI reference is served at free.ind.in/api/docs. The quickstart, authentication, code examples, and the full endpoint list are in the documentation. Automating with no-code tools? Start from the n8n, Make.com & Zapier recipes.